© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 28432
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_10_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     élarg
    0.52
     అవకాశ
    0.51
    豐
    0.50
    ይል
    0.47
     resultat
    0.46
    Limited
    0.46
     finiteness
    0.46
     Prozesse
    0.45
    眞
    0.45
     analyse
    0.45
    POSITIVE LOGITS
     a
    0.47
     th
    0.46
     και
    0.46
    EST
    0.46
    无
    0.46
     без
    0.45
    do
    0.45
     до
    0.45
     do
    0.45
     и
    0.44
    Activations Density 0.000%

    No Known Activations